Calculate the pooled estimate of variance

  • Thread starter Thread starter chwala
  • Start date Start date
  • Tags Tags
    Estimate Variance
Click For Summary
The discussion focuses on calculating the pooled estimate of variance using the formula for two sample variances. The calculated pooled variance is approximately 0.627165, which lies between the two original variances. There is a clarification regarding the use of arithmetic mean for uniform sample sizes rather than weighted averages. The hypothesis test is set up to compare the mean weights of boys and girls, leading to the rejection of the null hypothesis in favor of the alternative. The notation for the means is corrected to ensure clarity in the hypothesis statements.
chwala
Gold Member
Messages
2,827
Reaction score
415
Homework Statement
See attached
Relevant Equations
stats
1648466908376.png

OK, Let me attempt part (i), first,
Here we have;
##s^2_p ##=##\dfrac{ (n_1-1)s_1^2+(n_2-1)s_2^2}{n_1+n_2-2}##

##s^2_p ##=##\dfrac{ (7-1)0.63953+(7-1)0.6148}{7+7-2}##

##s^2_p ##=##\dfrac{3.83718+3.6888}{12}##

##s^2_p ##=##\dfrac{3.83718+3.6888}{12}##

##s^2_p ##=##\dfrac{7.52598}{12}##

##s^2_p ##=##0.627165## its located between the two original variances... correct? i do not have markscheme nor solutions...

* Reading on this topic now...the literature is really confusing on the so called population data (presumably all the n values in a given data set) and sample data...
 
Last edited:
Physics news on Phys.org
i) Your sample sizes are uniform, so there's no need for weighted averages here. Find the variance estimates for both populations and then take their arithmetic mean.
 
nuuskur said:
i) Your sample sizes are uniform, so there's no need for weighted averages here. Find the variance estimates for both populations and then take their arithmetic mean.
Ok mate i.e ##\dfrac {0.63953+0.6148}{2}##= ##\dfrac {1.25433}{2}=0.627165## .

For part (ii), Let, ##μ_1## and##μ_2## be the mean for boys and girls respectively, then
We want to test the hypothesis; as per the question...

##H_0##: ##μ_1##=##μ_2## - Mean weight of boys is equal to mean weight of girls.
##H_A##: ##μ_1##<##μ_2## - Mean weight of boys is less than the mean weight of girls.

Using the t-statistic and also considering that dof =##12##and ##α=0.05## then it follows that the critical value = ##-1.782##
We shall therefore have,
##t##=##\dfrac {2.5429-3.18571}{\sqrt{(0.627165^2(\frac {1}{6}+\frac {1}{6})}}##=##\dfrac {2.5429-3.18571}{0.256040263}##=##-2.5105 < -1.782 ## We thefore Reject the Null hypothesis and accept the Alternative hypothesis.
 
Last edited:
Your notation is overloaded. You likely mean ##\mu _1## for boys and ##\mu _2## for girls. Hypotheses are logical negations of one another. This is not the case right now.
 
nuuskur said:
Your notation is overloaded. You likely mean ##\mu _1## for boys and ##\mu _2## for girls. Hypotheses are logical negations of one another. This is not the case right now.
Amended ...sorry was a bit busy...
 
nuuskur said:
Your notation is overloaded. You likely mean ##\mu _1## for boys and ##\mu _2## for girls. Hypotheses are logical negations of one another. This is not the case right now.
Is it now correct?
 
First, I tried to show that ##f_n## converges uniformly on ##[0,2\pi]##, which is true since ##f_n \rightarrow 0## for ##n \rightarrow \infty## and ##\sigma_n=\mathrm{sup}\left| \frac{\sin\left(\frac{n^2}{n+\frac 15}x\right)}{n^{x^2-3x+3}} \right| \leq \frac{1}{|n^{x^2-3x+3}|} \leq \frac{1}{n^{\frac 34}}\rightarrow 0##. I can't use neither Leibnitz's test nor Abel's test. For Dirichlet's test I would need to show, that ##\sin\left(\frac{n^2}{n+\frac 15}x \right)## has partialy bounded sums...